ResearchBenchmarksLocomotion on MuJoCo Ant (Adversarial Robustness Testing)Follow4,574,311Target RewardPPO4,345,595.454,459,953.2254,574,3114,688,668.775Jun 6, 2024Evaluation ResultsMethodMethodLinksTarget RewardClean RewardTargeted PGD RewardMax Reward (SA-RL)Reward (BIA-ILfD Ours)Average Attack RewardPPODefense=No defenseDefense=No defense2024.064,574,311302,7353,975,2814,681,2024,423,1234,359TDRT-PPODefense=TDRTDefense=TDRT2024.064,574,3112,944,243276,387342,512327,8833,155